List your company

Multi-hop Question Answering on HotPotQA (Task Score, Brier)

57.6Task ScoreGEPA-C
55.41655.98356.5557.117May 20, 2026

Evaluation results

MethodLinks
GEPA-COptimizer LLM=GPT-52026.0557.60.41
GEPA-COptimizer LLM=GPT-5-mini2026.0557.60.41
GEPA-COptimizer LLM=Gemini-3.1-Pro2026.0557.60.41
GEPA-COptimizer LLM=Gemini-3.1-FL2026.0557.60.41
RPTOptimizer LLM=GPT-52026.0555.50.438
RPTOptimizer LLM=GPT-5-mini2026.0555.50.438
RPTOptimizer LLM=Gemini-3.1-Pro2026.0555.50.438
RPTOptimizer LLM=Gemini-3.1-FL2026.0555.50.438